Lynne bbe95f7353 x86: replace explicit REP_RETs with RETs ... From x86inc: > On AMD cpus <=K10, an ordinary ret is slow if it immediately follows either > a branch or a branch target. So switch to a 2-byte form of ret in that case. > We can automatically detect "follows a branch", but not a branch target. > (SSSE3 is a sufficient condition to know that your cpu doesn't have this problem.) x86inc can automatically determine whether to use REP_RET rather than REP in most of these cases, so impact is minimal. Additionally, a few REP_RETs were used unnecessary, despite the return being nowhere near a branch. The only CPUs affected were AMD K10s, made between 2007 and 2011, 16 years ago and 12 years ago, respectively. In the future, everyone involved with x86inc should consider dropping REP_RETs altogether.		2023-02-01 04:23:55 +01:00
..
aarch64
arm
riscv	checkasm: RISC-V 64-bit assembler test harness	2022-10-10 02:23:18 +02:00
x86	x86: replace explicit REP_RETs with RETs	2023-02-01 04:23:55 +01:00
.gitignore
aacpsdsp.c
af_afir.c
alacdsp.c
audiodsp.c	checkasm/audiodsp: Be strict about MMX	2022-10-11 14:18:54 +02:00
av_tx.c	x86/tx_float: add 15xN PFA FFT AVX SIMD	2022-09-23 12:35:27 +02:00
blockdsp.c	checkasm/blockdsp: Be strict about MMX	2022-10-11 14:18:54 +02:00
bswapdsp.c
checkasm.c	libavfilter/x86/vf_convolution: add sobel filter optimization and unit test with intel AVX512 VNNI	2022-11-14 10:04:16 +08:00
checkasm.h	libavfilter/x86/vf_convolution: add sobel filter optimization and unit test with intel AVX512 VNNI	2022-11-14 10:04:16 +08:00
exrdsp.c
fixed_dsp.c
flacdsp.c	avcodec/flacdsp: Remove unused function parameter	2022-08-05 03:28:45 +02:00
float_dsp.c
fmtconvert.c	avcodec/fmtconvert: Remove unused AVCodecContext parameter	2022-09-21 20:26:40 +02:00
g722dsp.c
h264dsp.c
h264pred.c
h264qpel.c
hevc_add_res.c	checkasm/hevc_add_res: add 12bit test	2022-08-16 14:00:34 +02:00
hevc_idct.c
hevc_pel.c
hevc_sao.c	checkasm: improve hevc_sao test	2022-05-25 08:04:58 +02:00
huffyuvdsp.c	checkasm/huffyuvdsp: Use declare_func_emms only when needed	2022-10-11 14:18:54 +02:00
idctdsp.c	checkasm/idctdsp: Use declare_func_emms only when needed	2022-10-11 14:18:54 +02:00
jpeg2000dsp.c
llviddsp.c	checkasm/llviddsp: Be strict about MMX	2022-10-11 14:18:54 +02:00
llviddspenc.c	checkasm/llviddspenc: Use declare_func_emms only when needed	2022-10-11 14:18:54 +02:00
lpc.c	tests/checkasm/lpc: correct arithmetic when randomizing buffers	2022-09-23 01:50:59 +02:00
Makefile	libavfilter/x86/vf_convolution: add sobel filter optimization and unit test with intel AVX512 VNNI	2022-11-14 10:04:16 +08:00
motion.c	checkasm: motion: Test different h parameters	2022-08-17 00:00:50 +03:00
opusdsp.c
pixblockdsp.c	checkasm/pixblockdsp: Be strict about MMX	2022-10-11 14:18:54 +02:00
sbrdsp.c
sw_gbrp.c
sw_rgb.c
sw_scale.c	checkasm: sw_scale: Produce more realistic test filter coefficients for yuv2yuvX	2022-08-19 22:54:51 +03:00
synth_filter.c	dca_core: convert to lavu/tx	2022-11-06 14:39:36 +01:00
utvideodsp.c
v210dec.c	checkasm/v210dec: add extra space to the destination arrays	2022-12-21 00:36:49 +01:00
v210enc.c	checkasm/v210enc: test the entire width of 10-bit planar input arrays	2022-12-01 18:19:03 +01:00
vc1dsp.c	checkasm/vc1dsp: Use declare_func_emms only when needed	2022-10-11 14:18:54 +02:00
vf_blend.c
vf_colorspace.c
vf_convolution.c	libavfilter/x86/vf_convolution: add sobel filter optimization and unit test with intel AVX512 VNNI	2022-11-14 10:04:16 +08:00
vf_eq.c
vf_gblur.c	avfilter/vf_gblur: Move ff_gblur_init into a header	2022-05-06 05:19:49 +02:00
vf_hflip.c	avfilter/vf_hflip: Move ff_hflip_init into a header	2022-05-06 05:19:50 +02:00
vf_nlmeans.c	avfilter/vf_nlmeans: Move ff_nlmeans_init into a header	2022-05-06 05:19:50 +02:00
vf_threshold.c	avfilter/vf_threshold: Move ff_threshold_init into a header	2022-05-06 05:19:50 +02:00
videodsp.c
vorbisdsp.c	tests/checkasm: add a test for VorbisDSPContext	2022-09-19 21:28:23 -03:00
vp8dsp.c	checkasm/vp8dsp: Use declare_func_emms only when needed	2022-10-08 09:33:36 +02:00
vp9dsp.c